Keith Chua
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
VEILED-SH: Vulnerability Expression through Indirect Language Evaluation Dataset (Self-Harm)
According to the abstract, Leanne Tan, Keith Chua, Shaun Khoo and colleagues introduce VEILED-SH, a benchmark of 10,003 prompts for how AI systems respond to indirect expressions of suicide, self-harm and distress, grounded in Singapore sources. Evaluating five systems, they report variation in proxy alignment across practitioner-calibrated profiles.